Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Añ
    -0.08
     pagar
    -0.08
     қой
    -0.08
    malloc
    -0.08
     futura
    -0.07
    (IF
    -0.07
    ],"
    -0.07
     библиот
    -0.07
    орами
    -0.07
    %),
    -0.07
    POSITIVE LOGITS
    -thirds
    0.09
    三个
    0.09
     നാല്
    0.09
     quartet
    0.09
    选四
    0.09
    组三
    0.09
     ನಾಲ
    0.09
    _three
    0.09
     మూడు
    0.09
     الثلاث
    0.09
    Act Density 0.100%

    No Known Activations